[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10},"actionData","errors","root",{"_121":122},"routes/modules.$creator.$moduleId",{"_14":15,"_16":17,"_18":19,"_20":21},"routes/modules.$creator.$moduleId.endpoints",{"_11":12,"_13":-5},"error","Module not found","tools","module",{"_20":22,"_23":24,"_25":26,"_27":28,"_29":30,"_31":32,"_33":34,"_35":26,"_36":37,"_38":-5,"_39":-5,"_40":41,"_42":43,"_44":45,"_46":47,"_48":49,"_50":49,"_51":52,"_53":54,"_55":56,"_57":-5,"_58":49,"_59":45,"_60":61,"_62":63,"_64":65,"_66":67,"_68":69,"_70":71,"_72":73,"_74":75,"_76":77,"_78":79,"_80":-5,"_81":-5,"_82":-5,"_83":84,"_85":-5,"_86":45,"_87":88,"_89":90,"_91":92,"_93":94,"_95":96,"_97":98},"apiUrl","https://odel.app/api","creator","urlpipe","moduleId","mcp","@urlpipe/mcp","displayName","URLpipe","tagline","Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse.","iconKey","external/180ac3ea507a579a794792415d9a828bec24898134b50ced40153eabea92b6e8.png","category","remote","status","published","visibility","public","metaDescription","deploymentType","external","workerName","bindingName","mcpConfig","{\"url\":\"https://urlpipe.dev/mcp\",\"transport\":\"streamable-http\",\"authType\":\"bearer\"}","pricingModel","free","priceCredits",0,"creatorUserId","system:external-import","createdAt",1790463490000,"updatedAt","sourceRegistry","official-mcp-registry","sourceUrl","https://registry.modelcontextprotocol.io/v0/servers?search=dev.urlpipe%2Fmcp","sourceVerified",true,"sourceMissingSince","importedAt","upstreamStars","upstreamUpdatedAt",1790347933000,"detectedTransport","streamable-http","detectedAuthType","none","probeStatus","ok","lastProbedAt",1790448172000,"githubRepoUrl","https://github.com/URLpipe/mcp","githubRepoFullName","URLpipe/mcp","releaseId","ext-urlpipe-mcp","version","1.2.0","descriptionMarkdown","

\n $\"URLpipe\"$ \n

\n\n

URLpipe MCP server

\n\n

\n Give your agent a browser that runs the page's JavaScript before it reads it.\n
\n Website ·\n Docs ·\n Pricing\n

\n\n

\n $\"smithery$ \n $\"URLpipe$ \n

\n\n---\n\nA plain `fetch` tool does an HTTP GET. On a site that builds itself in the browser —\nReact, Vue, most docs sites and dashboards — that returns an empty shell, and the agent\neither says it can't read the page or guesses what was on it.\n\nURLpipe loads every page in real Chrome first, then hands your agent what it asked\nfor: the page as Markdown, a screenshot it can look at, its metadata, its console\nerrors or a Lighthouse audit.\n\n- **Hosted.** Streamable HTTP at `https://urlpipe.dev/mcp`. Nothing to install or run.\n- **One bearer token.** Can be read-only, limited to one project, or set to expire.\n- **14 tools.** The nine API operations, plus results, request history, projects and usage.\n- **Same credits as the HTTP API.** 1,000 free every month, no card. Cached results cost nothing.\n- **Processed in the EU.** Fetching, rendering and storage happen in Europe.\n\nThis repository holds the server's registry entry ([`server.json`](https://github.com/URLpipe/mcp/blob/main/server.json)) and\nthe setup for each client. The server itself runs at urlpipe.dev.\n\n## Get a token\n\n1. [Sign up](https://urlpipe.dev) and confirm your email address.\n2. In the dashboard, open **Organization → MCP access** and create a token. Choose\n **Fetch pages and read results** for an agent that works normally, or **Read past\n results only** for one that must never spend credits.\n3. Copy it — it is shown once.\n\nEvery client sends it as `Authorization: Bearer YOUR_TOKEN`.\n\n## Connect your client\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http urlpipe https://urlpipe.dev/mcp \\\n --scope user \\\n --header \"Authorization: Bearer YOUR_TOKEN\"\n```\n\nOr share it with your team in `.mcp.json`, each person setting their own `URLPIPE_TOKEN`:\n\n```json\n{\n \"mcpServers\": {\n \"urlpipe\": {\n \"type\": \"http\",\n \"url\": \"https://urlpipe.dev/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer ${URLPIPE_TOKEN}\"\n }\n }\n }\n}\n```\n\n### Claude Desktop\n\nWhere your organization has request headers in **Customize → Connectors → Add custom\nconnector**, add `https://urlpipe.dev/mcp` with *No sign-in* and an `authorization`\nheader of `Bearer YOUR_TOKEN`. Otherwise use the open-source\n[mcp-remote](https://github.com/geelen/mcp-remote) bridge in\n`claude_desktop_config.json` (needs Node.js):\n\n```json\n{\n \"mcpServers\": {\n \"urlpipe\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"mcp-remote\",\n \"https://urlpipe.dev/mcp\",\n \"--header\",\n \"Authorization:${URLPIPE_AUTH}\",\n \"--transport\",\n \"http-only\"\n ],\n \"env\": {\n \"URLPIPE_AUTH\": \"Bearer YOUR_TOKEN\"\n }\n }\n }\n}\n```\n\n### Cursor\n\n`~/.cursor/mcp.json`, or `.cursor/mcp.json` in a project:\n\n```json\n{\n \"mcpServers\": {\n \"urlpipe\": {\n \"url\": \"https://urlpipe.dev/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer ${env:URLPIPE_TOKEN}\"\n }\n }\n }\n}\n```\n\n### VS Code\n\n`.vscode/mcp.json` — VS Code asks for the token once and stores it securely:\n\n```json\n{\n \"inputs\": [\n {\n \"type\": \"promptString\",\n \"id\": \"urlpipe-token\",\n \"description\": \"URLpipe MCP token\",\n \"password\": true\n }\n ],\n \"servers\": {\n \"urlpipe\": {\n \"type\": \"http\",\n \"url\": \"https://urlpipe.dev/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer ${input:urlpipe-token}\"\n }\n }\n }\n}\n```\n\n### Windsurf\n\n`mcp_config.json`:\n\n```json\n{\n \"mcpServers\": {\n \"urlpipe\": {\n \"serverUrl\": \"https://urlpipe.dev/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer ${env:URLPIPE_TOKEN}\"\n }\n }\n }\n}\n```\n\n### Cline\n\n`cline_mcp_settings.json`:\n\n```json\n{\n \"mcpServers\": {\n \"urlpipe\": {\n \"type\": \"streamableHttp\",\n \"url\": \"https://urlpipe.dev/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer YOUR_TOKEN\"\n },\n \"disabled\": false,\n \"autoApprove\": [\"list_projects\", \"get_usage\", \"get_result\"]\n }\n }\n}\n```\n\n### Zed\n\n`settings.json`:\n\n```json\n{\n \"context_servers\": {\n \"urlpipe\": {\n \"url\": \"https://urlpipe.dev/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer YOUR_TOKEN\"\n }\n }\n }\n}\n```\n\n### From a directory\n\nURLpipe is listed on [Smithery](https://smithery.ai/servers/urlpipe/urlpipe) and\n[Glama](https://glama.ai/mcp/connectors/dev.urlpipe/urlpipe), and in the official MCP\nRegistry as `dev.urlpipe/mcp`. On Smithery, paste your token as it is — the server\naccepts it with or without the `Bearer ` prefix.\n\nStep-by-step pages for each client, with a first prompt to try and troubleshooting,\nare at [urlpipe.dev/integrations](https://urlpipe.dev/integrations).\n\n## Tools\n\n| Tool | What it returns | Credits |\n|---|---|---:|\n| `list_projects` | The projects the token can reach. Start here: every fetching tool takes a `project_id`. | 0 |\n| `get_usage` | What the plan allows, what is left this period, and what each operation costs. | 0 |\n| `fetch_markdown` | The page's main content as clean Markdown, after its JavaScript ran. **The one to use for reading.** | 1 |\n| `fetch_html` | The rendered DOM — what a browser sees, not the shell curl gets. | 1 |\n| `capture_screenshot` | A full-page screenshot, returned as an image the model can look at. Viewport, device scale, dark mode, one element by selector, PNG/JPEG/WebP. | 1 |\n| `capture_console_errors` | `console.error` and `console.warn` during load, uncaught exceptions and unhandled promise rejections. | 1 |\n| `run_lighthouse_audit` | A real Lighthouse audit: performance, accessibility, best practices, SEO and Core Web Vitals. | 2 |\n| `extract_metadata` | Open Graph, Twitter card and page metadata reconciled into one object. | 5 |\n| `extract_keywords` | The 5–15 terms that best represent the page, ranked by a language model. | 15 |\n| `summarize_page` | A short Markdown summary of the page's main content. | 17 |\n| `scrape_url` | Several of the above from one page visit. Each operation is billed as usual. | sum |\n| `get_result` | The result of an earlier request, by its token. | 0 |\n| `list_requests` | A project's recent requests, newest first. | 0 |\n| `get_request` | Everything about one past request except its result: timings, cache, webhook delivery. | 0 |\n\n**Async is the default,** as it is over HTTP: a fetching tool returns a token straight\naway and `get_result` collects the result. Pass `sync: true` to wait for it instead.\nMost agents work this out from the tool descriptions; saying \"use sync: true\" in the\nprompt saves a round trip.\n\n**A repeated request is free.** Results are kept for 30 days and reused while they are\nfresher than `max_age` (7 days by default).\n\n`initialize` and `tools/list` answer without a token, so you can see the list above\nstraight from the server:\n\n```bash\ncurl -s https://urlpipe.dev/mcp \\\n -H \"Content-Type: application/json\" \\\n -H \"Accept: application/json, text/event-stream\" \\\n -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/list\"}'\n```\n\n## A first prompt\n\n```text\nUsing urlpipe with sync: true, read https://news.ycombinator.com as Markdown and list\nthe five top stories with their links. Then take a screenshot of the first story's page\nand tell me what the page looks like.\n```\n\n## What it doesn't do\n\nURLpipe answers questions about one URL at a time. It doesn't crawl whole sites,\ndiscover URLs, or reach `localhost` and private addresses — it fetches public pages\nfrom its own servers. It follows each site's robots.txt by default.\n\n## Links\n\n- [MCP server overview](https://urlpipe.dev/mcp-server)\n- [MCP docs](https://urlpipe.dev/docs/mcp) — tokens, scopes, limits\n- [HTTP API docs](https://urlpipe.dev/docs) and [OpenAPI spec](https://urlpipe.dev/openapi.json)\n- [Free tools](https://urlpipe.dev/tools) — try every operation without an account\n- Questions: contact@urlpipe.dev\n\nLicensed under MIT: the configuration and documentation in this repository.\nThe URLpipe service is covered by its [terms](https://urlpipe.dev/terms).\n","changelogMarkdown","videoKey","requiredSecretsJson","publishedAt",1790347224000,"priceCents","trialDays","iconType","image","upstream",{"_108":109,"_110":111,"_112":-5,"_113":114,"_115":116,"_117":118},"requiredSecrets",[],"tags",[101,102,103,104,105,106,107],"assets",[],"stats",{"_99":45,"_100":45},"ratingAvg","reviewCount","ai-agents","claude","headless-chrome","lighthouse","markdown","screenshot","web-scraping","topics",[101,102,103,104,105,21,119,120,106,107],"license","MIT","language","registryName","dev.urlpipe/mcp","homepage","https://urlpipe.dev/mcp-server","packages",[],"mcp-server","model-context-protocol","ENV",{"_123":124,"_125":126,"_127":128,"_129":-7},"ENVIRONMENT","production","TURNSTILE_SITE_KEY","0x4AAAAAAB8-rEI2gNDf_QhU","SENTRY_DSN","https://45fd1229f78089d5c3ee78be128030e1@o4510583261757440.ingest.de.sentry.io/4510584253448272","SENTRY_ENABLE_LOCAL"]